sanyuan0704/sanyuan-skillsPublic

What is sanyuan-skills?

A production-grade code review skill for Claude Code focusing heavily on SOLID principles and security.

What does sanyuan-skills do?

The Code Review Expert is a highly specialized, production-ready skill designed to be injected into AI agent terminals like Claude Code. It effectively acts as a rigorous senior software engineer, scrutinizing uncommitted git changes for structural integrity, boundary conditions, and security vulnerabilities. It strictly evaluates the code against established SOLID principles and architectural best practices, actively identifying inefficient algorithms and poor error handling. By providing expert-level, automated feedback directly in the terminal, it aims to significantly reduce technical debt before code is ever pushed to the repository.

Who is sanyuan-skills for?

Software engineers, tech leads, and developers who heavily utilize AI agent terminals and demand high-quality, secure code output. It requires Node.js and a compatible CLI agent tool to function.

How do I get started with sanyuan-skills?

npx skills add sanyuan0704/sanyuan-skills --path skills/code-review-expert

How popular is sanyuan-skills on GitHub?

sanyuan0704/sanyuan-skills has 3,931 stars and 344 forks on GitHub, and gained 6 stars in the last 7 days.

What license does sanyuan-skills use?

sanyuan0704/sanyuan-skills is released under the MIT license.

• Oct 4, 2026Previously tracked as sanyuan0704/code-review-expert; its 1 daily snapshot and 2 trending appearances were merged into this profile. Stars: 3,790 on 2026-07-29 under the old name, 3,931 on 2026-10-03 (+141).

• Permissive license

  MIT

• Continuous integration

  Automated checks passing

The Code Review Expert is a highly specialized, production-ready skill designed to be injected into AI agent terminals like Claude Code. It effectively acts as a rigorous senior software engineer, scrutinizing uncommitted git changes for structural integrity, boundary conditions, and security vulnerabilities. It strictly evaluates the code against established SOLID principles and architectural best practices, actively identifying inefficient algorithms and poor error handling. By providing expert-level, automated feedback directly in the terminal, it aims to significantly reduce technical debt before code is ever pushed to the repository.

Software engineers, tech leads, and developers who heavily utilize AI agent terminals and demand high-quality, secure code output. It requires Node.js and a compatible CLI agent tool to function.

• SOLID enforcement: Rigorously analyzes code architecture to ensure strict adherence to foundational object-oriented design principles.
• Security auditing: Actively scans uncommitted changes for common injection vulnerabilities and improperly handled boundary conditions.
• Performance evaluation: Identifies highly inefficient algorithms and potential execution bottlenecks within the newly written code.
• Error handling checks: Verifies that comprehensive error catching and graceful failure mechanisms are properly implemented.
• Terminal integration: Installs seamlessly via npx directly into Claude Code and other compatible AI CLI environments.

Getting started: npx skills add sanyuan0704/sanyuan-skills --path skills/code-review-expert

• public-apis/public-apis

  A collective list of free APIs

  486.1K stars · Python

• donnemartin/system-design-primer

  Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

  373.2K stars · Python

• practical-tutorials/project-based-learning

  Curated list of project-based tutorials

  285.8K stars · Python

• NousResearch/hermes-agent

  The agent that grows with you

  251.2K stars · Python

• yt-dlp/yt-dlp

  A feature-rich command-line audio/video downloader

  195.5K stars · Python

• microsoft/markitdown

  Python tool for converting files and office documents to Markdown.

  188.4K stars · Python